Hugging Face's logo

MattStammers
/
appo-mujoco_halfcheetah-approaching_sota

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
MattStammers commited on
Commit
a1e7c9e
•
1 Parent(s): 69709f1

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. .summary/0/events.out.tfevents.1703347292.rhmmedcatt-proliant-ml350-gen10 +3 -0
  3. .summary/1/events.out.tfevents.1703347292.rhmmedcatt-proliant-ml350-gen10 +3 -0
  4. README.md +189 -0
  5. checkpoint_p0/best_000730608_187047936_reward_2619.683.pth +3 -0
  6. checkpoint_p0/checkpoint_001966256_506757120.pth +3 -0
  7. checkpoint_p0/checkpoint_001966480_506871808.pth +3 -0
  8. checkpoint_p0/milestones/checkpoint_000046016_11780096.pth +3 -0
  9. checkpoint_p0/milestones/checkpoint_000092528_23691264.pth +3 -0
  10. checkpoint_p0/milestones/checkpoint_000138640_35495936.pth +3 -0
  11. checkpoint_p0/milestones/checkpoint_000184976_47357952.pth +3 -0
  12. checkpoint_p0/milestones/checkpoint_000231464_59260928.pth +3 -0
  13. checkpoint_p0/milestones/checkpoint_000277960_71163904.pth +3 -0
  14. checkpoint_p0/milestones/checkpoint_000324232_83009536.pth +3 -0
  15. checkpoint_p0/milestones/checkpoint_000370680_94904320.pth +3 -0
  16. checkpoint_p0/milestones/checkpoint_000417144_106799104.pth +3 -0
  17. checkpoint_p0/milestones/checkpoint_000463544_118677504.pth +3 -0
  18. checkpoint_p0/milestones/checkpoint_000509848_130531328.pth +3 -0
  19. checkpoint_p0/milestones/checkpoint_000556208_142401536.pth +3 -0
  20. checkpoint_p0/milestones/checkpoint_000602736_154312704.pth +3 -0
  21. checkpoint_p0/milestones/checkpoint_000649232_166215680.pth +3 -0
  22. checkpoint_p0/milestones/checkpoint_000695728_178118656.pth +3 -0
  23. checkpoint_p0/milestones/checkpoint_000742416_190070784.pth +3 -0
  24. checkpoint_p0/milestones/checkpoint_000788784_201940992.pth +3 -0
  25. checkpoint_p0/milestones/checkpoint_000835184_213819392.pth +3 -0
  26. checkpoint_p0/milestones/checkpoint_000880752_225484800.pth +3 -0
  27. checkpoint_p0/milestones/checkpoint_000926904_237305856.pth +3 -0
  28. checkpoint_p0/milestones/checkpoint_000973336_249192448.pth +3 -0
  29. checkpoint_p0/milestones/checkpoint_001019736_261070848.pth +3 -0
  30. checkpoint_p0/milestones/checkpoint_001066072_272932864.pth +3 -0
  31. checkpoint_p0/milestones/checkpoint_001112152_284729344.pth +3 -0
  32. checkpoint_p0/milestones/checkpoint_001156936_296198144.pth +3 -0
  33. checkpoint_p0/milestones/checkpoint_001203208_308043776.pth +3 -0
  34. checkpoint_p0/milestones/checkpoint_001249672_319938560.pth +3 -0
  35. checkpoint_p0/milestones/checkpoint_001295976_331792384.pth +3 -0
  36. checkpoint_p0/milestones/checkpoint_001342280_343646208.pth +3 -0
  37. checkpoint_p0/milestones/checkpoint_001388296_355426304.pth +3 -0
  38. checkpoint_p0/milestones/checkpoint_001434152_367165440.pth +3 -0
  39. checkpoint_p0/milestones/checkpoint_001480264_378970112.pth +3 -0
  40. checkpoint_p0/milestones/checkpoint_001526616_390840320.pth +3 -0
  41. checkpoint_p0/milestones/checkpoint_001572984_402710528.pth +3 -0
  42. checkpoint_p0/milestones/checkpoint_001619304_414572544.pth +3 -0
  43. checkpoint_p0/milestones/checkpoint_001665544_426409984.pth +3 -0
  44. checkpoint_p0/milestones/checkpoint_001711688_438222848.pth +3 -0
  45. checkpoint_p0/milestones/checkpoint_001758248_450142208.pth +3 -0
  46. checkpoint_p0/milestones/checkpoint_001804616_462012416.pth +3 -0
  47. checkpoint_p0/milestones/checkpoint_001851136_473923584.pth +3 -0
  48. checkpoint_p0/milestones/checkpoint_001897696_485842944.pth +3 -0
  49. checkpoint_p0/milestones/checkpoint_001943840_497655808.pth +3 -0
  50. checkpoint_p1/best_001898352_485998592_reward_2579.664.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ sf_log.txt filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1703347292.rhmmedcatt-proliant-ml350-gen10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfe2cdc26af76906ae6e73d5620674d498a4fc9f974bc9f889c052ed892d8b4
3
+ size 22594056
.summary/1/events.out.tfevents.1703347292.rhmmedcatt-proliant-ml350-gen10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9922c8989e8c4bd808c874e6d1296ec28a5ebe214feb779eaff8905e5690af6b
3
+ size 10647727
README.md ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: mujoco_halfcheetah
15
+ type: mujoco_halfcheetah
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 2480.36 +/- 56.37
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ ## About the Project
24
+
25
+ This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist).
26
+
27
+ In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this.
28
+
29
+ ## Project Aims
30
+
31
+ This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it anywhere near sota performance.
32
+
33
+ I then re-trained the models with 100 million timesteps- at this point 2 environments maxed out at sota performance (Pong and Freeway) with four approaching sota performance - (atlantis, boxing, tennis and fishingderby.) =6/57 near sota.
34
+
35
+ The aim now is to try and reach state-of-the-art (SOTA) performance on a further block of atari environments using up to 1 billion training timesteps initially with appo. I will flag the models with SOTA when they reach at or near these levels.
36
+
37
+ After this I will switch on V-Trace to see if the Impala variations perform any better with the same seed (I have seeded '1234')
38
+
39
+
40
+ ## About the Model
41
+
42
+ The hyperparameters used in the model are described in my shell script on my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his parameters, I saved time and energy by using many of his tuned hyperparameters to reduce carbon inefficiency:
43
+ ```
44
+ hyperparameters = {
45
+ "help": false,
46
+ "algo": "APPO",
47
+ "env": "atari_asteroid",
48
+ "experiment": "atari_asteroid_APPO",
49
+ "train_dir": "./train_atari",
50
+ "restart_behavior": "restart",
51
+ "device": "gpu",
52
+ "seed": 1234,
53
+ "num_policies": 2,
54
+ "async_rl": true,
55
+ "serial_mode": false,
56
+ "batched_sampling": true,
57
+ "num_batches_to_accumulate": 2,
58
+ "worker_num_splits": 1,
59
+ "policy_workers_per_policy": 1,
60
+ "max_policy_lag": 1000,
61
+ "num_workers": 16,
62
+ "num_envs_per_worker": 2,
63
+ "batch_size": 1024,
64
+ "num_batches_per_epoch": 8,
65
+ "num_epochs": 4,
66
+ "rollout": 128,
67
+ "recurrence": 1,
68
+ "shuffle_minibatches": false,
69
+ "gamma": 0.99,
70
+ "reward_scale": 1.0,
71
+ "reward_clip": 1000.0,
72
+ "value_bootstrap": false,
73
+ "normalize_returns": true,
74
+ "exploration_loss_coeff": 0.0004677351413,
75
+ "value_loss_coeff": 0.5,
76
+ "kl_loss_coeff": 0.0,
77
+ "exploration_loss": "entropy",
78
+ "gae_lambda": 0.95,
79
+ "ppo_clip_ratio": 0.1,
80
+ "ppo_clip_value": 1.0,
81
+ "with_vtrace": true,
82
+ "vtrace_rho": 1.0,
83
+ "vtrace_c": 1.0,
84
+ "optimizer": "adam",
85
+ "adam_eps": 1e-05,
86
+ "adam_beta1": 0.9,
87
+ "adam_beta2": 0.999,
88
+ "max_grad_norm": 0.0,
89
+ "learning_rate": 0.0003033891184,
90
+ "lr_schedule": "linear_decay",
91
+ "lr_schedule_kl_threshold": 0.008,
92
+ "lr_adaptive_min": 1e-06,
93
+ "lr_adaptive_max": 0.01,
94
+ "obs_subtract_mean": 0.0,
95
+ "obs_scale": 255.0,
96
+ "normalize_input": true,
97
+ "normalize_input_keys": [
98
+ "obs"
99
+ ],
100
+ "decorrelate_experience_max_seconds": 0,
101
+ "decorrelate_envs_on_one_worker": true,
102
+ "actor_worker_gpus": [],
103
+ "set_workers_cpu_affinity": true,
104
+ "force_envs_single_thread": false,
105
+ "default_niceness": 0,
106
+ "log_to_file": true,
107
+ "experiment_summaries_interval": 3,
108
+ "flush_summaries_interval": 30,
109
+ "stats_avg": 100,
110
+ "summaries_use_frameskip": true,
111
+ "heartbeat_interval": 10,
112
+ "heartbeat_reporting_interval": 60,
113
+ "train_for_env_steps": 100000000,
114
+ "train_for_seconds": 10000000000,
115
+ "save_every_sec": 120,
116
+ "keep_checkpoints": 2,
117
+ "load_checkpoint_kind": "latest",
118
+ "save_milestones_sec": 1200,
119
+ "save_best_every_sec": 5,
120
+ "save_best_metric": "reward",
121
+ "save_best_after": 100000,
122
+ "benchmark": false,
123
+ "encoder_mlp_layers": [
124
+ 512,
125
+ 512
126
+ ],
127
+ "encoder_conv_architecture": "convnet_atari",
128
+ "encoder_conv_mlp_layers": [
129
+ 512
130
+ ],
131
+ "use_rnn": false,
132
+ "rnn_size": 512,
133
+ "rnn_type": "gru",
134
+ "rnn_num_layers": 1,
135
+ "decoder_mlp_layers": [],
136
+ "nonlinearity": "relu",
137
+ "policy_initialization": "orthogonal",
138
+ "policy_init_gain": 1.0,
139
+ "actor_critic_share_weights": true,
140
+ "adaptive_stddev": false,
141
+ "continuous_tanh_scale": 0.0,
142
+ "initial_stddev": 1.0,
143
+ "use_env_info_cache": false,
144
+ "env_gpu_actions": false,
145
+ "env_gpu_observations": true,
146
+ "env_frameskip": 4,
147
+ "env_framestack": 4,
148
+ "pixel_format": "CHW"
149
+ }
150
+
151
+ ```
152
+
153
+
154
+
155
+ A(n) **APPO** impala model trained on the **mujoco_halfcheetah** environment.
156
+
157
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Sample factory is a
158
+ high throughput on-policy RL framework. I have been using
159
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
160
+
161
+
162
+ ## Downloading the model
163
+
164
+ After installing Sample-Factory, download the model with:
165
+ ```
166
+ python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-mujoco_halfcheetah
167
+ ```
168
+
169
+
170
+ ## Using the model
171
+
172
+ To run the model after download, use the `enjoy` script corresponding to this environment:
173
+ ```
174
+ python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_halfcheetah --train_dir=./train_dir --experiment=APPO-mujoco_halfcheetah
175
+ ```
176
+
177
+
178
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
179
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
180
+
181
+ ## Training with this model
182
+
183
+ To continue training with this model, use the `train` script corresponding to this environment:
184
+ ```
185
+ python -m sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_halfcheetah --train_dir=./train_dir --experiment=APPO-mujoco_halfcheetah --restart_behavior=resume --train_for_env_steps=10000000000
186
+ ```
187
+
188
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
189
+
checkpoint_p0/best_000730608_187047936_reward_2619.683.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924fc1aa1b7eff49559f60d8f22ba554fa279244084b617d8f33f5e13885d452
3
+ size 83071
checkpoint_p0/checkpoint_001966256_506757120.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a70b6726101add2f2aafec368e498e5e34bfd91507030658d28e47ef47331d2
3
+ size 83335
checkpoint_p0/checkpoint_001966480_506871808.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb43a2560f6324b782b731edeb978902a5748e085a2d04109205463d56643a4c
3
+ size 83335
checkpoint_p0/milestones/checkpoint_000046016_11780096.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bdadb076298f5cb7c8f3a1462ee8c7cc634bffc847148c2cce1add67c478c5a
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000092528_23691264.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4003fedf9031ab0da4caae77e9cc3e0b7c5849bf083a693c70892219b9cd99e7
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000138640_35495936.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c5ab18eb84ba9e46ee7bda190a1fecea3313654254cea3334ce63279f32df7e
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000184976_47357952.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1688fc0e0dfbbf41bf2296b7214ceef8b619d40a149eb714dcdbe890f4ec7d22
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000231464_59260928.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4617e35a517a1c45d6ee6714a840b9ab1138612ac8a4140aa6580b4c4942141a
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000277960_71163904.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee3054f514868b3e28f8499c5a17e1f0c91a80143d4eb353a0a37232e097e22
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000324232_83009536.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec1ae250f18d7026ae5ad9aa33dceeb57378e3d9aeb599798f834fc0d458877
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000370680_94904320.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25525e8481e6425ca624c47b7275305a94d1455cf565f68af05ebd0e7830fe50
3
+ size 84015
checkpoint_p0/milestones/checkpoint_000417144_106799104.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2eb63d8dedd6afa3a5af264410753b90cf47641b219de89a6f7355a08fe10c8
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000463544_118677504.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d9684dea4aa5e0d12286a34ed781e09c9204aa69938afd831acdd3e6ba47e4
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000509848_130531328.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d306d4f974e29ba730885daf6f228a9799f15614874e591bca656936ef89bb8c
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000556208_142401536.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ede9b24c17acb3ef70c9ce2845ab13767dee181e44f77ca475a03ee0c903b4a
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000602736_154312704.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cee5798260ce464bcf7a0ba390155dfdbe3c6bf46880137542112ddc0109ec
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000649232_166215680.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94812cdfc707458f167bf15b20c8bcde41dae50ed810a4fefbe5b8642e6fdab9
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000695728_178118656.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26a80d94a610589ece20218ab9fcfd39f6772d75438c88c01b48ad8763a6490
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000742416_190070784.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7549544b91a53fb18a62dcd039999b721bc92aaa03c46e40d01e9f10b7fa660a
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000788784_201940992.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f555520017352c7dc2168c2257ae64bc667e14227059d9a04becd76d30d43e07
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000835184_213819392.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd6fceef177b56fa03db064a7d2a89f5e59aa300bcad5eea3383c926cdb6089
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000880752_225484800.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d71e4bb3bb06cf84d692a40048dd236191977d96ba602a01bf8cd9593c0ccb00
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000926904_237305856.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caadad9dbf53a9febaafa30ed8b1263ffd6317476ac44533dc84558f752b11a8
3
+ size 84059
checkpoint_p0/milestones/checkpoint_000973336_249192448.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ba0a151b1a6902134c10bcbe75a5bfe9c0df662b55e36e693e4b3ecdce4e26
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001019736_261070848.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c703a97a723ac675224c40b5be60dd07a7aa7cf5be0e25aa6ec3616221192d93
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001066072_272932864.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c54bd092fe651a4ad172b6e5389416a1054d348fa73cf47722ba8f057cc8759
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001112152_284729344.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5918a2e982746335f7b78e5f934943dc8438f321d915f9962fb7ef38df492257
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001156936_296198144.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daff21956a6c9aa4498ee08a7100e1134ab3aa5f8128790947cdb506d5facc7b
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001203208_308043776.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5fd383685660685af93bbc55fd6a92eca36d5de96c7e13315bb40c35de2f8aa
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001249672_319938560.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300c1fc9f10dc46412c04db0164b65e813893384dacb5c2f63c88ca2ac70ad99
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001295976_331792384.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b586f9f68742d8698cfdfaaa2ae54f38ee7215d66bf61f9e54dee3cd7fe3ec9c
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001342280_343646208.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e424ad93d938f52ce879e2704c467579b9a7fd817e8d5d540fee64f5ee557a
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001388296_355426304.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7c1f365d59190de3008fab1bb46d70438b5598e2b6ec1aaefff47d9947adbf
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001434152_367165440.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e01dfd69e1280ff3e345eec50002e15ae4ddfee51b04d98adeb7cd8ee2f6c2
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001480264_378970112.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab8fc100207f55c4be43734d2d1e8a91b271e7a73f4d4f6c40394589cb1a39f
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001526616_390840320.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c443a63212306da5ddb08630febb128688cba94c65eeb9d645ed9497fc5fb8
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001572984_402710528.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87de8168d317a3d6e08537d2406862a6a2bed207aaaa041fd0adbc98da0ca80
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001619304_414572544.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e812903f708eda3b69e757d69415f947fb5bd2b48244b207eb65c35b5ad2972f
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001665544_426409984.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30645007168a736f5a6baf453343c0e67937c65633e066ba7096fbf1cba9abf
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001711688_438222848.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7056cfcf7eadec8ab9e0d7f1a5bee82ac36f19911f0a0aa649c617e333c1135
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001758248_450142208.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7266d86a952b69487556bb1d79c9a8aeee61534cb0d1c9533dc521a0a0f203bb
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001804616_462012416.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0aff7df0498d8aaa1418d004d9f042065f66007a910b4deae0764c24848188f
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001851136_473923584.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd78cf0d436ba3e121266088e8384be6db6511f13716edb4ac029a625b7d59a1
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001897696_485842944.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c8562917b64d2eadd87e942047ad0ab6a5f6d64d0d36a95ef2498a33b9bfee
3
+ size 84059
checkpoint_p0/milestones/checkpoint_001943840_497655808.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb013fd480d28e40570cb94d74ed53903cd933f9ff3b8160fdf87da96809b578
3
+ size 84059
checkpoint_p1/best_001898352_485998592_reward_2579.664.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ad77416b3dde3cf85f46f893241040d82b67649e70e2ae0dd8c48d709b7a7cf
3
+ size 83071